# Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher

arXiv: https://arxiv.org/abs/2004.08780 · HTML: https://mlsanity.com/paper/2004.08780/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 22 of 22)

- [Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://mlsanity.com/paper/2202.04770/) (2022)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Data Augmentation for Electrocardiograms](https://mlsanity.com/paper/2204.04360/) (2022)
- [Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey](https://mlsanity.com/paper/2310.10060/) (2023)
- [Fighting Money Laundering with Statistics and Machine Learning](https://mlsanity.com/paper/2201.04207/) (2022)
- [Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder](https://mlsanity.com/paper/2306.06579/) (2023)
- [DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification](https://mlsanity.com/paper/2103.01119/) (2021)
- [IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation](https://mlsanity.com/paper/2602.15878/) (2026)
- [Data Augmentation for Multivariate Time Series Classification: An Experimental Study](https://mlsanity.com/paper/2406.06518/) (2024)
- [ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data](https://mlsanity.com/paper/2412.10912/) (2024)
- [DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generation](https://mlsanity.com/paper/2509.18584/) (2025)
- [On Mini-Batch Training with Varying Length Time Series](https://mlsanity.com/paper/2212.06536/) (2022)
- [Invariant Features for Global Crop Type Classification](https://mlsanity.com/paper/2509.03497/) (2025)
- [Learning Time-Scale Invariant Population-Level Neural Representations](https://mlsanity.com/paper/2511.13022/) (2025)
- [Assessing unconstrained surgical cuttings in VR using CNNs](https://mlsanity.com/paper/2205.00934/) (2022)
- [Hybrid data driven/thermal simulation model for comfort assessment](https://mlsanity.com/paper/2309.01734/) (2023)
- [Overcoming Data Limitations in Internet Traffic Forecasting: LSTM Models with Transfer Learning and Wavelet Augmentation](https://mlsanity.com/paper/2409.13181/) (2024)
- [Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments](https://mlsanity.com/paper/2505.03825/) (2025)
- [Sliding-Window Reordering with Overlap Averaging: A Simple Time-Domain Augmentation for Multivariate Forecasting](https://mlsanity.com/paper/2604.09067/) (2026)
- [Preserving Temporal Dynamics in Time Series Generation](https://mlsanity.com/paper/2604.27182/) (2026)
- [Modality vs. Morphology: A Framework for Time Series Classification for Biological Signals](https://mlsanity.com/paper/2605.18483/) (2026)
- [IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation](https://mlsanity.com/paper/2605.27397/) (2026)

## Abstract (arXiv)

Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are often small. In order to address this problem, we propose a novel time series data augmentation called guided warping. While many data augmentation methods are based on random transformations, guided warping exploits the element alignment properties of Dynamic Time Warping (DTW) and shapeDTW, a high-level DTW method based on shape descriptors, to deterministically warp sample patterns. In this way, the time series are mixed by warping the features of a sample pattern to match the time steps of a reference pattern. Furthermore, we introduce a discriminative teacher in order to serve as a directed reference for the guided warping. We evaluate the method on all 85 datasets in the 2015 UCR Time Series Archive with a deep convolutional neural network (CNN) and a recurrent neural network (RNN). The code with an easy to use implementation can be found at https://github.com/uchidalab/time_series_augmentation .